Method for screening open reading frame with small peptide encoding capacity

• Main Authors: GUO LI, YU JIAFENG, LIU JIAN, DOU XIANGHUA, QIAN BOWEN, JIANG WENWEN, GONG LEJUN
• Format: Patent
• Language: Chinese; English
• Published: 06.11.2020
• Subjects: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention belongs to the technical field of medicines and particularly relates to a method for screening an open reading frame with small peptide encoding capacity. The method comprises the following steps: with the GC content of a genome as a basis, screening prokaryotic genomes with sORFs annotations from a database; grouping the prokaryotic genomes according to the GC contents of the genomes; then, screening out the sORFs with clear biological functions in each genome; conducting redundancy elimination processing by utilizing a CD-Hit program; sequentially taking peptide coded sORFs ineach genome as positive samples and corresponding random disordered sequences as negative samples, taking the positive samples and the negative samples as a preliminary training set to respectively predict sORFs in other genomes, and taking the genome with the best prediction effect in each genome GC content interval as a final training set source genome; and based on the screened training set, conducting training with a